content-research-writer
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured instructions for assisting users with writing, outlining, and researching content. It does not include any scripts, external dependencies, or commands that interact with sensitive system resources.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided drafts and external research materials, which is an inherent part of its functionality. While this constitutes a potential surface for indirect prompt injection, the instructions emphasize a collaborative workflow with human-in-the-loop review, and the skill lacks any dangerous capabilities (such as automated command execution or network exfiltration) that would make such an injection exploitable.
Audit Metadata